Water supply network leakage identification method and system based on satellite monitoring and medium

Abstract

The invention relates to the technical field of pipe network leakage identification, and particularly provides a water supply pipe network leakage identification method and system based on satellite monitoring and a medium, and the method comprises the steps: obtaining SAR satellite time sequence data of a target region; processing SAR satellite time sequence data to obtain backscattering coefficient time sequence variation and earth surface time sequence deformation information; humidity abnormal points are extracted based on the time sequence variation, and deformation abnormal points are extracted based on the deformation information; the humidity abnormal points and the deformation abnormal points are subjected to spatial superposition screening with a water supply pipe network buffer area, time sequence correlation analysis is carried out after screening, and suspected leakage points are obtained; and according to a multi-parameter decision rule, screening out points which simultaneously meet conditions of spatial proximity, humidity anomaly, deformation anomaly and time sequence synchronization, and taking the points as high-confidence suspected leakage points. According to the method, the change of the surface humidity is reflected by using the change quantity of the backscattering coefficient, and the humidity abnormity and the surface deformation are taken as a joint criterion, so that the accuracy of leakage point identification is greatly improved.

Description

Technical Field

[0001] This invention belongs to the field of pipeline network leakage identification technology, and particularly relates to a method, system and medium for identifying leakage in water supply pipeline networks based on satellite monitoring. Background Technology

[0002] Water supply networks are a core component of urban infrastructure, directly impacting residents' daily lives, industrial production, and public safety. However, leakage in water supply networks has been a long-standing and increasingly serious problem globally. According to statistics from the International Water Association, leakage rates in some regions are as high as 30% or more. This not only results in enormous waste of water and energy resources but also significantly increases water treatment costs and the operational burden on water supply companies. More seriously, long-term, hidden leaks can erode foundations, causing secondary disasters such as road collapses, and may also lead to water pollution, threatening water supply security.

[0003] To address the aforementioned issues, it is necessary to identify and locate leak points. Currently, commonly used methods for monitoring and identifying leaks in water supply networks fall into two categories: First, traditional ground-based detection techniques, mainly including line inspection using listening poles and correlator analysis. While these methods offer relatively accurate location, they are inefficient, costly, and reliant on manual labor, making them unsuitable for large-scale, complex urban areas. Second, methods based on flow and pressure detection, which involve setting up independent metering zones and installing high-precision flow meters and pressure sensors at the zone entrances to macroscopically determine the area where leaks occur. However, these methods cannot precisely pinpoint the leak points and still require coordination with ground-based investigations, and involve substantial initial investment.

[0004] In recent years, remote sensing technologies such as synthetic aperture radar interferometry have been introduced into the field of leak detection, becoming an emerging research direction due to their advantages of wide coverage, non-contact operation, and all-weather capability. This technology indirectly infers the location of potential leaks by monitoring micro-deformations of the land surface or changes in soil dielectric properties. However, existing satellite leak detection methods rely too heavily on a single, indirect physical quantity: soil moisture content (or vegetation index). In complex urban environments, non-target factors such as garden irrigation, rainwater accumulation, construction drainage, and leaks from non-water supply pipelines can also cause abnormal soil moisture, leading to numerous false alarms. Therefore, existing methods generate a large number of invalid alarms, requiring significant investment of manpower and resources for on-site verification, resulting in low verification efficiency and a need to significantly improve the final leak detection rate. Summary of the Invention

[0005] To address the problems existing in the prior art, this invention provides a method for identifying leakage in water supply networks based on satellite monitoring, comprising the following steps: S1: Acquire SAR satellite time-series data, water supply network geographic information data, and DEM data for the target area; S2: Process the SAR satellite time series data to obtain the time series variation of backscattering coefficient and the time series deformation information of the Earth's surface; S3: Extract humidity anomalies based on the temporal variation of backscattering coefficient, and extract deformation anomalies based on the temporal deformation information of the land surface. S4: Spatial overlay screening of the humidity anomaly points and deformation anomaly points with the water supply network buffer zone, followed by temporal correlation analysis to obtain suspected leakage points. S5: Based on the preset multi-parameter decision rules, select points that simultaneously meet the conditions of spatial proximity, abnormal humidity, abnormal deformation, and time synchronization, and output them as high-confidence suspected leakage points.

[0006] Based on the above scheme, the SAR satellite time series data includes SLC time series data and GRD time series data. The method for obtaining the time series variation of the backscattering coefficient in step S2 is as follows: S21: Using the DEM data, perform radiometric calibration, speckle filtering, and terrain correction on the GRD data; S22: Calculate the backscattering coefficient value for each image in the GRD time series; S23: Based on the backscattering coefficient value of each image and the backscattering coefficient value of the reference reference, the temporal variation of the backscattering coefficient is obtained. The reference reference is an image of the extreme drought period in a specific period of the target area.

[0007] Preferably, the method for obtaining the temporal deformation information of the land surface is as follows: Based on the DEM data, the SLC data is processed using PSI technology to obtain the temporal deformation information of the land surface at each PS point. The temporal deformation information of the land surface includes the average deformation rate and the temporal deformation amount.

[0008] Based on the above scheme, step S3 specifically includes: S31: Based on the temporal variation of the backscattering coefficient and the humidity threshold, filter out pixels with abnormal humidity; S32: Based on deformation rate and deformation rate threshold, filter settlement points.

[0009] Specifically, step S31 includes: S311: When the temporal variation of the backscattering coefficient is greater than the humidity threshold, the pixel is marked as abnormal; otherwise, it is marked as normal. S312: For each pixel, identify and record the length of the continuous sequence marked as an anomaly, and determine the observation period during which the anomaly persists; S313: Identify humidity anomalies based on the observation period and duration threshold of the anomaly.

[0010] Based on the above scheme, the time-series correlation analysis includes: S41: For spatially overlapping points, obtain the time sequence of the humidity anomaly pixels and the settling points respectively; S42: Calculate the correlation coefficient based on the time series sequence described in S41; S43: Set a correlation threshold, and determine whether humidity and settling velocity are synchronized based on the correlation coefficient and the correlation threshold.

[0011] Preferably, the preset multi-parameter decision rule includes: R1: Determine whether the location of the suspected leak point is within the preset distance buffer zone of the water supply network; R2: Determine whether the persistent humidity abnormality at the suspected leakage point exceeds the duration threshold; R3: Determine whether the deformation rate of a suspected leakage point is less than the deformation rate threshold; R4: Determine whether the humidity anomaly and deformation anomaly at the suspected leakage point are significantly correlated over time.

[0012] On the other hand, the present invention also provides a water supply network leakage identification system based on satellite monitoring, used to implement the water supply network leakage identification method as described above, the system comprising: The data acquisition module is used to acquire SAR satellite time-series data, water supply network geographic information data, and DEM data of the target area; The data processing module is used to process the SAR satellite time series data to obtain the time series variation of the backscattering coefficient and the time series deformation information of the land surface; The anomaly analysis module is used to extract persistent humidity anomalies based on the temporal variation of the backscattering coefficient and to extract deformation anomalies based on the temporal deformation information of the land surface. The spatiotemporal analysis module is used to spatially overlay and filter the humidity anomaly points and deformation anomaly points with the water supply network buffer zone, and then perform temporal correlation analysis to obtain suspected leakage points. The leakage decision module is used to filter out points that simultaneously meet the conditions of spatial proximity, abnormal humidity, abnormal deformation, and time synchronization according to preset multi-parameter decision rules, and output them as high-confidence suspected leakage points.

[0013] Preferably, the system generates a thematic map of the spatial distribution of high-confidence suspected leak points based on the high-confidence suspected leak points.

[0014] The present invention also provides a computer-readable storage medium having a computer program, which, when executed by a processor, implements the steps of the pipeline leakage identification method described above.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention obtains the backscattering coefficient and calculates the change in the backscattering coefficient to reflect the change in surface humidity. It uses humidity anomaly and surface subsidence as a joint criterion, effectively eliminating interference factors such as irrigation and rainfall, greatly improving the accuracy of leak point identification and reducing the false alarm rate. 2. This invention determines humidity anomalies based on change detection, eliminating the need for complex model inversion and avoiding inversion errors caused by inaccurate parameters such as vegetation and roughness. It directly reflects the relative change trend of surface humidity relative to the drought state through change detection, and stably identifies abnormally humid areas caused by long-term seepage. 3. By judging persistent anomalies, transient anomalies caused by short-term environmental disturbances are effectively filtered out. Suspected leakage points are identified through spatial overlay analysis and time-series correlation analysis. Interference factors are further eliminated, and high-confidence suspected leakage points are screened, which significantly improves the accuracy and reliability of leakage identification results. 4. This method is an automated process for data acquisition, processing, analysis, and decision-making. It is suitable for large-scale rapid screening and verification based on the output results, which greatly improves inspection efficiency, shortens the repair cycle, and saves resources. Attached Figure Description

[0016] Figure 1 This is an overall flowchart of the leakage identification method of this application; Figure 2 This is a structural diagram of the leakage identification method of this application. Detailed Implementation

[0017] The invention will be further described below with reference to specific embodiments.

[0018] like Figure 1 and Figure 2 As shown, this embodiment provides a method for identifying water supply network leakage based on satellite monitoring, including the following steps: S1: Acquire SAR satellite time-series data, water supply network geographic information data, and DEM data for the target area; Specifically, S1 includes: The Sentinel-1 satellite acquires time-series data over a certain period of time covering the target area. This time-series data includes SLC time-series data and GRD time-series data. The SLC time-series data is used for deformation detection, and the GRD time-series data is used for humidity change detection. Simultaneously acquire vector data of the water supply network and digital elevation model (DEM) data within the same time period.

[0019] In this embodiment, Sentinel-1 data from the most recent 1-2 years is used. Sentinel-1 has a short revisit period, and the sampling interval is sufficient to capture the evolution trend of slowly developing leakage sedimentation and recurring humidity anomalies.

[0020] S2: Process the SAR satellite time series data to obtain the time series variation of backscattering coefficient and the time series deformation information of the Earth's surface; The method for obtaining the temporal variation of the backscattering coefficient in step S2 is as follows: S21: Using the DEM data, perform radiometric calibration, speckle filtering, and terrain correction on the GRD data; in S21, the DEM data is used to perform terrain correction on the GRD data to eliminate geometric distortion and radiometric distortion caused by terrain.

[0021] S22: Calculate the backscattering coefficient value for each image in the GRD time series: ; It is important to note that σ 0 ( t ) represents the radar backscattering coefficient at time t. σ 0 ( t The linear value of ) has a very large dynamic range, which is not convenient for display, analysis and comparison between different scenarios. Therefore, this embodiment converts it into a normalized decibel value. To represent the backscattering coefficient value, in this application This represents the backscattering coefficient value of the pixel at time t.

[0022] S23: Backscattering coefficient value based on each image scene Backscattering coefficient value compared to reference standard The temporal variation of the backscattering coefficient is obtained: ; in, The backscattering coefficient value of the pixel at the reference time. This is the reference time.

[0023] The reference baseline is imagery of the target region during periods of extreme drought within a specific cycle. This represents the radar scattering intensity of a pixel under extreme drought conditions. >0 indicates that the pixel is in The time period is wetter than the dry period, and vice versa. The temporal change of the backscattering coefficient directly reflects the change in surface humidity relative to the extreme drought state.

[0024] This invention reflects humidity changes through the backscattering coefficient. Because water significantly increases the dielectric constant of the soil, it leads to the attenuation of radar echo energy. Under the condition of relatively stable surface cover, the continuous reduction of backscattering can serve as an effective indicator of long-term soil moisture.

[0025] In this embodiment, the method for obtaining the temporal deformation information of the land surface is as follows: Based on the DEM data, the SLC data is processed using Persistent Scatterer Interferometry (PSI) to obtain the temporal deformation information of the surface at each Persistent Scatterer (PS) point. The temporal deformation information includes the average deformation rate v and the temporal deformation d(t).

[0026] Those skilled in the art should know that before PSI technology processing, SLC data needs to undergo preprocessing operations such as precise orbit application, image registration, interferogram generation, flattening, and terrain phase removal. Among these, DEM data can simulate and remove terrain phase to assist SLC data in generating differential interferograms.

[0027] In this embodiment, the temporal deformation information of the surface of permanent scatterer points located within the preset buffer area of ​​the water supply network is selected first to provide high-quality data for subsequent fusion analysis.

[0028] S3: Extract persistent humidity anomalies based on the temporal variation of the backscattering coefficient, and extract deformation anomalies based on the temporal deformation information of the land surface; In this embodiment, through analysis In the time series analysis, pixels exceeding a duration threshold are identified as outliers. Step S3 specifically includes: S31: Set humidity threshold Based on the temporal variation of the backscattering coefficient and the humidity threshold, samples that continuously or repeatedly appear... The pixels are used as humidity anomalies; Step S31 specifically includes: S311: For each pixel, perform time-series binarization. When the condition is met, the pixel is marked as 1, indicating that the pixel is abnormal; otherwise, it is marked as 0, indicating that the pixel is normal. S312: Scan the binary sequence, identify all consecutive sequences marked as 1, and record the length of each consecutive sequence to determine how many observation periods the anomaly lasted; S313: Set duration threshold A humidity anomaly is identified when the observation period of the anomaly is greater than or equal to the duration threshold.

[0029] In this embodiment, let The value is 3. When the observation period of a certain pixel is abnormal for ≥3 consecutive periods, the pixel is a humidity abnormal pixel.

[0030] S32: Set deformation rate threshold If the deformation rate of point PS is less than the deformation rate threshold, it is a settlement point, and the settlement point is regarded as a deformation anomaly point.

[0031] S4: Spatially overlay the humidity anomaly points and deformation anomaly points with the geographical location of the pipeline network, and then perform time-series correlation analysis to identify suspected leakage points; First, buffer analysis is performed on the vector data of the water supply network in the target area to obtain the water supply network buffer. Humidity anomalies and deformation anomalies are spatially superimposed on the water supply network buffer, and spatially overlapping humidity anomalies and deformation anomalies are filtered. Then, a temporal correlation analysis is performed on the spatially overlapping points, the temporal correlation analysis including: S41: For spatially overlapping points, obtain the time sequence of the humidity anomaly points and the time sequence of the deformation anomaly points respectively; S42: Calculate the Pearson correlation coefficient R based on the time series obtained in S41. ; Where R represents the correlation between humidity change and deformation over the same time period. and It is the first Humidity changes and deformation at each time point and These are the means of their respective time series. The value range is [-1, 1].

[0032] S43: Set the correlation threshold Based on the correlation coefficient and correlation threshold, it is determined whether humidity and deformation are synchronized. If R is greater, it indicates that as humidity continues to increase, sedimentation slows down or tends to stabilize. The larger R is, the higher the synchronization between humidity and deformation time sequence.

[0033] Based on the analysis in step S4, further screening is conducted according to the temporal synchronization of humidity anomalies and deformation anomalies in the image to obtain suspected missing points.

[0034] S5: Based on the preset multi-parameter decision rules, select points that simultaneously meet the conditions of spatial proximity, abnormal humidity, abnormal deformation, and time synchronization, and output them as high-confidence suspected leakage points.

[0035] According to this application, the preset multi-parameter decision rules include: R1: Determine whether the location of the suspected leakage point is within the buffer zone of the water supply network; R2: Determine whether the persistent humidity at the suspected leakage point exceeds the duration threshold; R3: Determine whether the deformation rate of the suspected leakage point is less than the deformation rate threshold; R4: Determine whether the humidity anomaly and deformation anomaly at the suspected leakage point are significantly correlated over time.

[0036] If all rules R1-R4 are satisfied simultaneously, then this point is a high-confidence suspected leakage point.

[0037] Those skilled in the art will understand that the same image will be extracted for humidity anomalies and deformation anomalies separately. That is, a point will have two attribute values, and both attribute values ​​need to meet the rules. Finally, a high-confidence suspected missing point that meets the rules will be output.

[0038] According to this embodiment, by fusing the temporal deformation information of the ground surface from SAR satellites such as Sentinel-1 with the temporal variation information of radar backscattering, and supplementing it with geographic information data of the pipeline network, a multi-parameter decision model is constructed, thereby achieving high-precision and high-efficiency identification and location of leakage points in a large-scale urban water supply network.

[0039] According to other embodiments of the present invention, the acquisition of data of the target area in step S1 further includes optical images, which play an auxiliary role in identifying pipeline leakage points, specifically: After identifying suspected leakage points, high-resolution optical images from the same period were retrieved. The optical images were used to check whether there were any visible signs of water leakage at the suspected leakage points, such as abnormally lush vegetation or darkened ground, which further corroborated the evidence and increased the probability that the suspected leakage points were leaking.

[0040] In addition, optical images can be used to generate masks to conceal water bodies, dense forests, or areas with dense buildings, preventing interference with radar signals.

[0041] Based on the same technical concept, the present invention also provides a water supply network leakage identification system based on satellite monitoring, used to implement the above-described water supply network leakage identification method, the system comprising: The data acquisition module integrates multi-source input interfaces to acquire SAR satellite time-series data, water supply network geographic information data, and DEM data of the target area. The data processing module is used to process the SAR satellite time series data to obtain the time series variation of backscattering coefficient and the time series deformation information of the land surface, and to realize GRD / SLC standardization processing and feature extraction. The anomaly analysis module is used to perform humidity and deformation anomaly detection, extract persistent humidity anomaly points based on the temporal variation of the backscattering coefficient, and extract deformation anomaly points based on the temporal deformation information of the land surface. The spatiotemporal analysis module is used to perform spatial overlay and temporal correlation analysis on the humidity anomaly points, deformation anomaly points and the geographical location of the pipeline network to identify suspected leakage points; The leakage decision module is used to filter out points that simultaneously meet the conditions of spatial proximity, abnormal humidity, abnormal deformation, and time synchronization according to preset multi-parameter decision rules, and output them as high-confidence suspected leakage points.

[0042] Preferably, the system generates a thematic map of the spatial distribution of high-confidence suspected leaks and a list of high-confidence suspected leaks based on the high-confidence suspected leaks, for ground verification.

[0043] In this embodiment, the system can operate fully automatically, is suitable for city-level pipeline network surveys, significantly reduces the cost of manual inspections, and improves the efficiency and accuracy of leak detection.

[0044] Furthermore, the water supply network leakage identification method according to the present invention can be recorded in a computer-readable recording medium. Specifically, according to the present invention, a computer-readable recording medium storing computer-executable instructions can be provided, which, when executed by a processor, causes the processor to perform the water supply network leakage identification method as described above.

[0045] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code containing at least one executable instruction for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0046] In general, various exemplary embodiments of the present invention can be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of embodiments of the present invention are illustrated or described as block diagrams, flowcharts, or represented using certain other images, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or certain combinations thereof.

[0047] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0048] While the specific embodiments of the present invention have been described above, they are not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for identifying leakage in a water supply network based on satellite monitoring, characterized in that, Includes the following steps: S1: Acquire SAR satellite time-series data, water supply network geographic information data, and DEM data for the target area; S2: Process the SAR satellite time series data to obtain the time series variation of backscattering coefficient and the time series deformation information of the Earth's surface; S3: Extract humidity anomalies based on the temporal variation of the backscattering coefficient, and extract deformation anomalies based on the temporal deformation information of the land surface. S4: Spatial overlay screening of the humidity anomaly points and deformation anomaly points with the water supply network buffer zone, followed by temporal correlation analysis to obtain suspected leakage points. S5: Based on the preset multi-parameter decision rules, select points that simultaneously meet the conditions of spatial proximity, abnormal humidity, abnormal deformation, and time synchronization, and output them as high-confidence suspected leakage points.

2. The method for identifying water supply network leakage based on satellite monitoring according to claim 1, characterized in that, The SAR satellite time series data includes SLC time series data and GRD time series data. The method for obtaining the time series variation of the backscattering coefficient in step S2 is as follows: S21: Using the DEM data, perform radiometric calibration, speckle filtering, and terrain correction on the GRD data; S22: Calculate the backscattering coefficient value for each image in the GRD time series; S23: Based on the backscattering coefficient value of each image and the backscattering coefficient value of the reference reference, the temporal variation of the backscattering coefficient is obtained. The reference reference is an image of the extreme drought period in a specific period of the target area.

3. The method for identifying water supply network leakage based on satellite monitoring according to claim 2, characterized in that, The method for obtaining the temporal deformation information of the land surface is as follows: Based on the DEM data, the SLC data is processed using PSI technology to obtain the temporal deformation information of the land surface at each PS point. The temporal deformation information of the land surface includes the average deformation rate and the temporal deformation amount.

4. The method for identifying water supply network leakage based on satellite monitoring according to claim 3, characterized in that, Step S3 specifically includes: S31: Based on the temporal variation of the backscattering coefficient and the humidity threshold, filter out pixels with abnormal humidity; S32: Based on deformation rate and deformation rate threshold, filter settlement points.

5. The method for identifying water supply network leakage based on satellite monitoring according to claim 4, characterized in that, Step S31 specifically includes: S311: When the temporal variation of the backscattering coefficient is greater than the humidity threshold, the pixel is marked as abnormal; otherwise, it is marked as normal. S312: For each pixel, identify and record the length of the continuous sequence marked as an anomaly, and determine the observation period during which the anomaly persists; S313: Identify humidity anomalies based on the observation period and duration threshold of the anomaly.

6. The method for identifying water supply network leakage based on satellite monitoring according to claim 1, characterized in that, The time-series correlation analysis includes: S41: For spatially overlapping points, obtain the time sequence of the humidity anomaly points and deformation anomaly points respectively; S42: Calculate the correlation coefficient based on the time series sequence described in S41; S43: Based on the correlation coefficient and correlation threshold, determine whether humidity and settling velocity are synchronized.

7. The method for identifying water supply network leakage based on satellite monitoring according to claim 6, characterized in that, The preset multi-parameter decision rules include: R1: Determine whether the suspected leak point is located within the water supply network buffer zone; R2: Determine whether the persistent humidity abnormality at the suspected leakage point exceeds the duration threshold; R3: Determine whether the deformation rate of a suspected leakage point is less than the deformation rate threshold; R4: Determine whether the humidity anomaly and deformation anomaly at the suspected leakage point are significantly correlated over time.

8. A water supply network leakage identification system based on satellite monitoring, characterized in that, For implementing the water supply network leakage identification method as described in any one of claims 1-7, the system comprises: The data acquisition module is used to acquire SAR satellite time-series data, water supply network geographic information data, and DEM data of the target area; The data processing module is used to process the SAR satellite time series data to obtain the time series variation of the backscattering coefficient and the time series deformation information of the land surface; The anomaly analysis module is used to extract persistent humidity anomalies based on the temporal variation of the backscattering coefficient and to extract deformation anomalies based on the temporal deformation information of the land surface. The spatiotemporal analysis module is used to spatially overlay and filter the humidity anomaly points and deformation anomaly points with the water supply network buffer zone, and then perform temporal correlation analysis to obtain suspected leakage points. The leakage decision module is used to filter out points that simultaneously meet the conditions of spatial proximity, abnormal humidity, abnormal deformation, and time synchronization according to preset multi-parameter decision rules, and output them as high-confidence suspected leakage points.

9. The water supply network leakage identification system based on satellite monitoring according to claim 8, characterized in that, The system generates a thematic map of the spatial distribution of high-confidence suspected leak points based on the high-confidence suspected leak points.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium has a computer program that, when executed by a processor, implements the pipeline leakage identification method as described in any one of claims 1-7.

Images